1 files changed, 86 insertions, 297 deletions

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index c1bed89b1026..0e3a9b38bef2 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -22,57 +22,22 @@
 #include "iommu.h"
 #include "pasid.h"
 #include "perf.h"
+#include "../iommu-pages.h"
 #include "trace.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
 
-static DEFINE_XARRAY_ALLOC(pasid_private_array);
-static int pasid_private_add(ioasid_t pasid, void *priv)
-{
-	return xa_alloc(&pasid_private_array, &pasid, priv,
-			XA_LIMIT(pasid, pasid), GFP_ATOMIC);
-}
-
-static void pasid_private_remove(ioasid_t pasid)
-{
-	xa_erase(&pasid_private_array, pasid);
-}
-
-static void *pasid_private_find(ioasid_t pasid)
-{
-	return xa_load(&pasid_private_array, pasid);
-}
-
-static struct intel_svm_dev *
-svm_lookup_device_by_dev(struct intel_svm *svm, struct device *dev)
-{
-	struct intel_svm_dev *sdev = NULL, *t;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(t, &svm->devs, list) {
-		if (t->dev == dev) {
-			sdev = t;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return sdev;
-}
-
 int intel_svm_enable_prq(struct intel_iommu *iommu)
 {
 	struct iopf_queue *iopfq;
-	struct page *pages;
 	int irq, ret;
 
-	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER);
-	if (!pages) {
+	iommu->prq = iommu_alloc_pages_node(iommu->node, GFP_KERNEL, PRQ_ORDER);
+	if (!iommu->prq) {
 		pr_warn("IOMMU: %s: Failed to allocate page request queue\n",
 			iommu->name);
 		return -ENOMEM;
 	}
-	iommu->prq = page_address(pages);
 
 	irq = dmar_alloc_hwirq(IOMMU_IRQ_ID_OFFSET_PRQ + iommu->seq_id, iommu->node, iommu);
 	if (irq <= 0) {
@@ -117,7 +82,7 @@ free_hwirq:
 	dmar_free_hwirq(irq);
 	iommu->pr_irq = 0;
 free_prq:
-	free_pages((unsigned long)iommu->prq, PRQ_ORDER);
+	iommu_free_pages(iommu->prq, PRQ_ORDER);
 	iommu->prq = NULL;
 
 	return ret;
@@ -140,7 +105,7 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
 		iommu->iopf_queue = NULL;
 	}
 
-	free_pages((unsigned long)iommu->prq, PRQ_ORDER);
+	iommu_free_pages(iommu->prq, PRQ_ORDER);
 	iommu->prq = NULL;
 
 	return 0;
@@ -168,94 +133,32 @@ void intel_svm_check(struct intel_iommu *iommu)
 	iommu->flags |= VTD_FLAG_SVM_CAPABLE;
 }
 
-static void __flush_svm_range_dev(struct intel_svm *svm,
-				  struct intel_svm_dev *sdev,
-				  unsigned long address,
-				  unsigned long pages, int ih)
-{
-	struct device_domain_info *info = dev_iommu_priv_get(sdev->dev);
-
-	if (WARN_ON(!pages))
-		return;
-
-	qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, address, pages, ih);
-	if (info->ats_enabled) {
-		qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid,
-					 svm->pasid, sdev->qdep, address,
-					 order_base_2(pages));
-		quirk_extra_dev_tlb_flush(info, address, order_base_2(pages),
-					  svm->pasid, sdev->qdep);
-	}
-}
-
-static void intel_flush_svm_range_dev(struct intel_svm *svm,
-				      struct intel_svm_dev *sdev,
-				      unsigned long address,
-				      unsigned long pages, int ih)
-{
-	unsigned long shift = ilog2(__roundup_pow_of_two(pages));
-	unsigned long align = (1ULL << (VTD_PAGE_SHIFT + shift));
-	unsigned long start = ALIGN_DOWN(address, align);
-	unsigned long end = ALIGN(address + (pages << VTD_PAGE_SHIFT), align);
-
-	while (start < end) {
-		__flush_svm_range_dev(svm, sdev, start, align >> VTD_PAGE_SHIFT, ih);
-		start += align;
-	}
-}
-
-static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
-				unsigned long pages, int ih)
-{
-	struct intel_svm_dev *sdev;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(sdev, &svm->devs, list)
-		intel_flush_svm_range_dev(svm, sdev, address, pages, ih);
-	rcu_read_unlock();
-}
-
-static void intel_flush_svm_all(struct intel_svm *svm)
-{
-	struct device_domain_info *info;
-	struct intel_svm_dev *sdev;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(sdev, &svm->devs, list) {
-		info = dev_iommu_priv_get(sdev->dev);
-
-		qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, 0, -1UL, 0);
-		if (info->ats_enabled) {
-			qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid,
-						 svm->pasid, sdev->qdep,
-						 0, 64 - VTD_PAGE_SHIFT);
-			quirk_extra_dev_tlb_flush(info, 0, 64 - VTD_PAGE_SHIFT,
-						  svm->pasid, sdev->qdep);
-		}
-	}
-	rcu_read_unlock();
-}
-
 /* Pages have been freed at this point */
 static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 					struct mm_struct *mm,
 					unsigned long start, unsigned long end)
 {
-	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
+	struct dmar_domain *domain = container_of(mn, struct dmar_domain, notifier);
 
-	if (start == 0 && end == -1UL) {
-		intel_flush_svm_all(svm);
+	if (start == 0 && end == ULONG_MAX) {
+		cache_tag_flush_all(domain);
 		return;
 	}
 
-	intel_flush_svm_range(svm, start,
-			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
+	/*
+	 * The mm_types defines vm_end as the first byte after the end address,
+	 * different from IOMMU subsystem using the last address of an address
+	 * range.
+	 */
+	cache_tag_flush_range(domain, start, end - 1, 0);
 }
 
 static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 {
-	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
-	struct intel_svm_dev *sdev;
+	struct dmar_domain *domain = container_of(mn, struct dmar_domain, notifier);
+	struct dev_pasid_info *dev_pasid;
+	struct device_domain_info *info;
+	unsigned long flags;
 
 	/* This might end up being called from exit_mmap(), *before* the page
 	 * tables are cleared. And __mmu_notifier_release() will delete us from
@@ -269,157 +172,78 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 * page) so that we end up taking a fault that the hardware really
 	 * *has* to handle gracefully without affecting other processes.
 	 */
-	rcu_read_lock();
-	list_for_each_entry_rcu(sdev, &svm->devs, list)
-		intel_pasid_tear_down_entry(sdev->iommu, sdev->dev,
-					    svm->pasid, true);
-	rcu_read_unlock();
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
+		info = dev_iommu_priv_get(dev_pasid->dev);
+		intel_pasid_tear_down_entry(info->iommu, dev_pasid->dev,
+					    dev_pasid->pasid, true);
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+}
 
+static void intel_mm_free_notifier(struct mmu_notifier *mn)
+{
+	kfree(container_of(mn, struct dmar_domain, notifier));
 }
 
 static const struct mmu_notifier_ops intel_mmuops = {
 	.release = intel_mm_release,
 	.arch_invalidate_secondary_tlbs = intel_arch_invalidate_secondary_tlbs,
+	.free_notifier = intel_mm_free_notifier,
 };
 
-static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
-			     struct intel_svm **rsvm,
-			     struct intel_svm_dev **rsdev)
-{
-	struct intel_svm_dev *sdev = NULL;
-	struct intel_svm *svm;
-
-	if (pasid == IOMMU_PASID_INVALID || pasid >= PASID_MAX)
-		return -EINVAL;
-
-	svm = pasid_private_find(pasid);
-	if (IS_ERR(svm))
-		return PTR_ERR(svm);
-
-	if (!svm)
-		goto out;
-
-	/*
-	 * If we found svm for the PASID, there must be at least one device
-	 * bond.
-	 */
-	if (WARN_ON(list_empty(&svm->devs)))
-		return -EINVAL;
-	sdev = svm_lookup_device_by_dev(svm, dev);
-
-out:
-	*rsvm = svm;
-	*rsdev = sdev;
-
-	return 0;
-}
-
 static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 				   struct device *dev, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct intel_iommu *iommu = info->iommu;
 	struct mm_struct *mm = domain->mm;
-	struct intel_svm_dev *sdev;
-	struct intel_svm *svm;
+	struct dev_pasid_info *dev_pasid;
 	unsigned long sflags;
+	unsigned long flags;
 	int ret = 0;
 
-	svm = pasid_private_find(pasid);
-	if (!svm) {
-		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
-		if (!svm)
-			return -ENOMEM;
-
-		svm->pasid = pasid;
-		svm->mm = mm;
-		INIT_LIST_HEAD_RCU(&svm->devs);
-
-		svm->notifier.ops = &intel_mmuops;
-		ret = mmu_notifier_register(&svm->notifier, mm);
-		if (ret) {
-			kfree(svm);
-			return ret;
-		}
-
-		ret = pasid_private_add(svm->pasid, svm);
-		if (ret) {
-			mmu_notifier_unregister(&svm->notifier, mm);
-			kfree(svm);
-			return ret;
-		}
-	}
+	dev_pasid = kzalloc(sizeof(*dev_pasid), GFP_KERNEL);
+	if (!dev_pasid)
+		return -ENOMEM;
 
-	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
-	if (!sdev) {
-		ret = -ENOMEM;
-		goto free_svm;
-	}
+	dev_pasid->dev = dev;
+	dev_pasid->pasid = pasid;
 
-	sdev->dev = dev;
-	sdev->iommu = iommu;
-	sdev->did = FLPT_DEFAULT_DID;
-	sdev->sid = PCI_DEVID(info->bus, info->devfn);
-	if (info->ats_enabled) {
-		sdev->qdep = info->ats_qdep;
-		if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS)
-			sdev->qdep = 0;
-	}
+	ret = cache_tag_assign_domain(to_dmar_domain(domain), dev, pasid);
+	if (ret)
+		goto free_dev_pasid;
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
 	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	if (ret)
-		goto free_sdev;
+		goto unassign_tag;
 
-	list_add_rcu(&sdev->list, &svm->devs);
+	spin_lock_irqsave(&dmar_domain->lock, flags);
+	list_add(&dev_pasid->link_domain, &dmar_domain->dev_pasids);
+	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
 	return 0;
 
-free_sdev:
-	kfree(sdev);
-free_svm:
-	if (list_empty(&svm->devs)) {
-		mmu_notifier_unregister(&svm->notifier, mm);
-		pasid_private_remove(pasid);
-		kfree(svm);
-	}
+unassign_tag:
+	cache_tag_unassign_domain(to_dmar_domain(domain), dev, pasid);
+free_dev_pasid:
+	kfree(dev_pasid);
 
 	return ret;
 }
 
-void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid)
-{
-	struct intel_svm_dev *sdev;
-	struct intel_svm *svm;
-	struct mm_struct *mm;
-
-	if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev))
-		return;
-	mm = svm->mm;
-
-	if (sdev) {
-		list_del_rcu(&sdev->list);
-		kfree_rcu(sdev, rcu);
-
-		if (list_empty(&svm->devs)) {
-			if (svm->notifier.ops)
-				mmu_notifier_unregister(&svm->notifier, mm);
-			pasid_private_remove(svm->pasid);
-			kfree(svm);
-		}
-	}
-}
-
 /* Page request queue descriptor */
 struct page_req_dsc {
 	union {
 		struct {
 			u64 type:8;
 			u64 pasid_present:1;
-			u64 priv_data_present:1;
-			u64 rsvd:6;
+			u64 rsvd:7;
 			u64 rid:16;
 			u64 pasid:20;
 			u64 exe_req:1;
@@ -438,7 +262,8 @@ struct page_req_dsc {
 		};
 		u64 qw_1;
 	};
-	u64 priv_data[2];
+	u64 qw_2;
+	u64 qw_3;
 };
 
 static bool is_canonical_address(u64 addr)
@@ -572,24 +397,6 @@ static void intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
 		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
 		event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
 	}
-	if (desc->priv_data_present) {
-		/*
-		 * Set last page in group bit if private data is present,
-		 * page response is required as it does for LPIG.
-		 * iommu_report_device_fault() doesn't understand this vendor
-		 * specific requirement thus we set last_page as a workaround.
-		 */
-		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
-		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
-		event.fault.prm.private_data[0] = desc->priv_data[0];
-		event.fault.prm.private_data[1] = desc->priv_data[1];
-	} else if (dmar_latency_enabled(iommu, DMAR_LATENCY_PRQ)) {
-		/*
-		 * If the private data fields are not used by hardware, use it
-		 * to monitor the prq handle latency.
-		 */
-		event.fault.prm.private_data[0] = ktime_to_ns(ktime_get());
-	}
 
 	iommu_report_device_fault(dev, &event);
 }
@@ -597,39 +404,23 @@ static void intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
 static void handle_bad_prq_event(struct intel_iommu *iommu,
 				 struct page_req_dsc *req, int result)
 {
-	struct qi_desc desc;
+	struct qi_desc desc = { };
 
 	pr_err("%s: Invalid page request: %08llx %08llx\n",
 	       iommu->name, ((unsigned long long *)req)[0],
 	       ((unsigned long long *)req)[1]);
 
-	/*
-	 * Per VT-d spec. v3.0 ch7.7, system software must
-	 * respond with page group response if private data
-	 * is present (PDP) or last page in group (LPIG) bit
-	 * is set. This is an additional VT-d feature beyond
-	 * PCI ATS spec.
-	 */
-	if (!req->lpig && !req->priv_data_present)
+	if (!req->lpig)
 		return;
 
 	desc.qw0 = QI_PGRP_PASID(req->pasid) |
 			QI_PGRP_DID(req->rid) |
 			QI_PGRP_PASID_P(req->pasid_present) |
-			QI_PGRP_PDP(req->priv_data_present) |
 			QI_PGRP_RESP_CODE(result) |
 			QI_PGRP_RESP_TYPE;
 	desc.qw1 = QI_PGRP_IDX(req->prg_index) |
 			QI_PGRP_LPIG(req->lpig);
 
-	if (req->priv_data_present) {
-		desc.qw2 = req->priv_data[0];
-		desc.qw3 = req->priv_data[1];
-	} else {
-		desc.qw2 = 0;
-		desc.qw3 = 0;
-	}
-
 	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
@@ -697,7 +488,7 @@ bad_req:
 
 		intel_svm_prq_report(iommu, dev, req);
 		trace_prq_report(iommu, dev, req->qw_0, req->qw_1,
-				 req->priv_data[0], req->priv_data[1],
+				 req->qw_2, req->qw_3,
 				 iommu->prq_seq_number++);
 		mutex_unlock(&iommu->iopf_lock);
 prq_advance:
@@ -736,7 +527,7 @@ void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
 	struct intel_iommu *iommu = info->iommu;
 	u8 bus = info->bus, devfn = info->devfn;
 	struct iommu_fault_page_request *prm;
-	bool private_present;
+	struct qi_desc desc;
 	bool pasid_present;
 	bool last_page;
 	u16 sid;
@@ -744,42 +535,25 @@ void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
 	prm = &evt->fault.prm;
 	sid = PCI_DEVID(bus, devfn);
 	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
-	private_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
 	last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
 
-	/*
-	 * Per VT-d spec. v3.0 ch7.7, system software must respond
-	 * with page group response if private data is present (PDP)
-	 * or last page in group (LPIG) bit is set. This is an
-	 * additional VT-d requirement beyond PCI ATS spec.
-	 */
-	if (last_page || private_present) {
-		struct qi_desc desc;
-
-		desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) |
-				QI_PGRP_PASID_P(pasid_present) |
-				QI_PGRP_PDP(private_present) |
-				QI_PGRP_RESP_CODE(msg->code) |
-				QI_PGRP_RESP_TYPE;
-		desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page);
-		desc.qw2 = 0;
-		desc.qw3 = 0;
-
-		if (private_present) {
-			desc.qw2 = prm->private_data[0];
-			desc.qw3 = prm->private_data[1];
-		} else if (prm->private_data[0]) {
-			dmar_latency_update(iommu, DMAR_LATENCY_PRQ,
-				ktime_to_ns(ktime_get()) - prm->private_data[0]);
-		}
+	desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) |
+			QI_PGRP_PASID_P(pasid_present) |
+			QI_PGRP_RESP_CODE(msg->code) |
+			QI_PGRP_RESP_TYPE;
+	desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page);
+	desc.qw2 = 0;
+	desc.qw3 = 0;
 
-		qi_submit_sync(iommu, &desc, 1, 0);
-	}
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 static void intel_svm_domain_free(struct iommu_domain *domain)
 {
-	kfree(to_dmar_domain(domain));
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	/* dmar_domain free is deferred to the mmu free_notifier callback. */
+	mmu_notifier_put(&dmar_domain->notifier);
 }
 
 static const struct iommu_domain_ops intel_svm_domain_ops = {
@@ -787,14 +561,29 @@ static const struct iommu_domain_ops intel_svm_domain_ops = {
 	.free			= intel_svm_domain_free
 };
 
-struct iommu_domain *intel_svm_domain_alloc(void)
+struct iommu_domain *intel_svm_domain_alloc(struct device *dev,
+					    struct mm_struct *mm)
 {
 	struct dmar_domain *domain;
+	int ret;
 
 	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!domain)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
+
 	domain->domain.ops = &intel_svm_domain_ops;
+	domain->use_first_level = true;
+	INIT_LIST_HEAD(&domain->dev_pasids);
+	INIT_LIST_HEAD(&domain->cache_tags);
+	spin_lock_init(&domain->cache_lock);
+	spin_lock_init(&domain->lock);
+
+	domain->notifier.ops = &intel_mmuops;
+	ret = mmu_notifier_register(&domain->notifier, mm);
+	if (ret) {
+		kfree(domain);
+		return ERR_PTR(ret);
+	}
 
 	return &domain->domain;
 }